@inproceedings{yu-etal-2026-camo,
    title = "{CAMO}: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in {LLM} Agent Simulations",
    author = "Yu, Xiangning  and
      Guo, Yuwei  and
      Hou, Yuqi  and
      Xue, Xiao  and
      Ma, Qun",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1224/",
    pages = "24447--24479",
    ISBN = "979-8-89176-395-1",
    abstract = "LLM-empowered agent simulations are increasingly used to study social emergence, yet the micro-to-macro causal mechanisms behind macro outcomes often remain unclear. This is challenging because emergence arises from intertwined agent interactions and meso-level feedback and nonlinearity, making generative mechanisms hard to disentangle. To this end, we introduce \textbf{CAMO}, an automated \textbf{Ca}usal discovery framework from \textbf{M}icr\textbf{o} behaviors to \textbf{M}acr\textbf{o} Emergence in LLM agent simulations. CAMO converts mechanistic hypotheses into computable factors grounded in simulation records and learns a compact causal representation centered on an emergent target . CAMO outputs a computable Markov boundary and a minimal upstream explanatory subgraph, yielding interpretable causal chains and actionable intervention levers. It also uses simulator-internal counterfactual probing to orient ambiguous edges and revise hypotheses when evidence contradicts the current view. Experiments across four emergent settings demonstrate the promise of CAMO.[The code is available at an anonymous link: {\ensuremath{<}}https://anonymous.4open.science/r/CAMO-0E6C/{\ensuremath{>}}.]"
}